© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215737
    Prev
    Next
    INDEX
    Explanations

    etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    েব
    0.27
     yǐ
    0.26
     технологі
    0.26
    ቴክ
    0.26
     TECHN
    0.26
     법
    0.25
     substandard
    0.25
     б
    0.25
    TECHN
    0.25
     întâm
    0.25
    POSITIVE LOGITS
    logging
    0.26
    riy
    0.25
    skull
    0.25
    orer
    0.25
     joyería
    0.24
    leri
    0.24
    io
    0.24
    ;
    0.24
    cli
    0.24
    mj
    0.23
    Activations Density 0.017%

    No Known Activations